etetoolkit
by K-Dense-AIetetoolkit is a phylogenetic tree toolkit for ETE workflows. Use the etetoolkit skill to parse, edit, compare, root, prune, and visualize trees in Newick, NHX, PhyloXML, or NeXML. It supports phylogenomics, orthology/paralogy analysis, NCBI taxonomy, and publication-style PDF or SVG output.
This skill scores 79/100 and is worth listing: it gives directory users a credible, domain-specific ETE workflow for phylogenetic tree analysis, with enough concrete examples to reduce guesswork versus a generic prompt. It is not a perfect install page because it lacks companion files and an install command, but the SKILL.md is substantial and operationally clear enough for an informed adoption decision.
- Strong domain fit: clearly targets ETE phylogenetic tree work, including Newick/NHX I/O, tree manipulation, evolutionary event detection, orthology/paralogy, taxonomy, and visualization.
- Substantial operational content: the body is large and includes code fences, workflow signals, and concrete tree-analysis examples that help an agent trigger and use it correctly.
- Good repository credibility: valid frontmatter, no placeholder markers, and no experimental/test-only signals in the skill content.
- No install command and no support files/scripts/references, so users must infer setup and library availability from the markdown alone.
- The repo appears to be documentation-heavy rather than tool-backed, so adoption may require extra manual interpretation for environment and dependency assumptions.
Overview of etetoolkit skill
What etetoolkit is for
The etetoolkit skill helps you work with ETE, a Python toolkit for phylogenetic and hierarchical tree analysis. It is most useful when you need to parse, edit, compare, root, prune, or visualize trees from formats like Newick, NHX, PhyloXML, or NeXML. If you are looking for the etetoolkit skill because you need practical support for phylogenomics or tree-based analysis, this skill is aimed at that workflow rather than generic Python scripting.
Best fit for this skill
Use etetoolkit when your task involves tree manipulation plus biological context: evolutionary event detection, orthology/paralogy inference, NCBI taxonomy lookup, or publication-style tree rendering in PDF or SVG. It is a strong fit for researchers and agents that need to move from a raw tree file to a curated analysis output with fewer manual steps.
What makes it worth installing
The main value of etetoolkit install is that it gives you a focused, tree-centric workflow instead of a broad prompt that guesses at phylogenetics. The skill is best when the input is already a tree, a clade list, or a phylogenomic question with clear taxonomic scope. It is less useful if you only need a generic plotting library or a simple file conversion.
How to Use etetoolkit skill
Install and locate the guidance
Install with npx skills add K-Dense-AI/claude-scientific-skills --skill etetoolkit. After installation, start with scientific-skills/etetoolkit/SKILL.md and read the sections on core capabilities and example patterns before you try to use the skill in a workflow. Since this repository does not provide extra rules/, resources/, or helper scripts, the main source of truth is the skill document itself.
Turn a rough goal into a usable prompt
For best etetoolkit usage, state the tree format, what you want changed, and the expected output. Good inputs are specific, such as: “Prune this Newick tree to these taxa, midpoint-root it, and export SVG,” or “Compare two trees and summarize the Robinson-Foulds distance.” Avoid vague prompts like “analyze my tree,” because the skill is optimized for concrete tree operations, not open-ended hypothesis generation.
Practical workflow that improves results
A good etetoolkit guide workflow is: load the tree, confirm the format, inspect the tip labels, apply one transformation at a time, then export and validate the result. If you are doing etetoolkit for Data Analysis, include the biological context up front: organism names, clade membership, whether branch lengths matter, and whether the tree is rooted. That context determines whether pruning, rerooting, or comparison is the correct first move.
What to read first in the repo
Read the overview and the code examples before copying anything into production. Pay special attention to the sections covering tree I/O, traversal, topology modification, distance calculations, and tree comparison. Those are the parts that most affect whether the skill fits your use case and whether your downstream analysis will be reproducible.
etetoolkit skill FAQ
Is etetoolkit only for biologists?
No. The etetoolkit skill is built around phylogenetic and hierarchical tree analysis, so biologists are the main audience, but any workflow that depends on structured tree operations can benefit. If you do clustering or taxonomy-aware tree manipulation, it can still be relevant.
Do I need this instead of a normal prompt?
Use the skill when you want a repeatable etetoolkit usage pattern with tree-specific operations and output expectations. A normal prompt may work for a one-off question, but it is easier to make mistakes with rooting, pruning, or tree format handling when the task is not framed as a structured skill workflow.
Is it beginner-friendly?
Yes, if you already know what tree you have and what outcome you want. It is not a substitute for learning phylogenetic basics, so beginners should expect to provide clearer inputs than they would for a generic coding task. The skill helps most when you know whether you need comparison, visualization, or topology editing.
When should I not use it?
Do not reach for etetoolkit if your job is only basic charting, sequence alignment, or non-tree biological analysis. It is also a poor fit if you have no tree file or no decision about format, rooting, or target taxa. In those cases, a broader analysis workflow is more appropriate than an etetoolkit install.
How to Improve etetoolkit skill
Give the model the right tree context
The biggest quality gain comes from stating the tree source and constraints clearly. Include the input format, whether branch lengths are meaningful, whether labels are stable, and whether you want to preserve branch lengths during pruning. For etetoolkit for Data Analysis, also provide species names, taxa to keep or exclude, and the intended reporting style.
Specify the operation sequence
The skill performs better when you break the job into ordered steps instead of asking for a single broad result. Example: “Read this Newick tree, prune to these taxa, reroot on the outgroup, compute RF distance against the reference tree, then export SVG.” That kind of prompt reduces ambiguity and makes etetoolkit usage much more reliable.
Watch for common failure modes
The most common problems are mismatched labels, unsupported assumptions about rooting, and asking for a visualization before the tree has been cleaned. If the first output looks wrong, do not just ask for a prettier version; verify the input tree, confirm the format, and check whether the requested taxa actually exist in the tree.
Iterate with validation, not just refinement
After the first pass, compare the exported tree or summary against your expected topology and taxa list. If something is off, refine by providing a smaller sample tree, a clearer outgroup, or a direct list of node names. That is the fastest way to improve etetoolkit guide results without drifting into generic, low-signal prompting.
